© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 39488
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to processing and thought

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.05
    4:0.23
    5:0.03
    6:0.04
    7:0.28
    8:0.03
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
     Shine
    -1.54
    ipedia
    -1.40
    ayne
    -1.40
     Shoes
    -1.39
    ウ
    -1.38
    osponsors
    -1.37
     Shed
    -1.37
    atown
    -1.36
     Contribut
    -1.35
    alia
    -1.34
    POSITIVE LOGITS
     incoming
    1.90
     breeze
    1.43
     input
    1.39
     queries
    1.39
     sacrament
    1.35
     motions
    1.34
     proposition
    1.31
     transferring
    1.29
     stimuli
    1.28
     passing
    1.27
    Activations Density 0.008%

    No Known Activations